codebook_data <- import("positive_results_in_registered_reports_masterfile_data.xlsx")
# Read codebook from second sheet in Excel file.
dict <- import("positive_results_in_registered_reports_masterfile_data.xlsx", sheet = "data_dictionary")
# Add variable labels to data (from Excel file)
var_label(codebook_data) <- dict_to_list(dict)
# Add value labels to data (manually)
val_labels(codebook_data$include_in_analysis) <- c("excluded" = 0, "included" = 1)
val_labels(codebook_data$is_RR) <- c("SR" = 0, "RR"= 1)
val_labels(codebook_data$support_binary) <- c("no support" = 0, "partial or full support" = 1)
val_labels(codebook_data$is_replication) <- c("is not a replication" = 0, "is a replication" = 1)
val_labels(codebook_data$contains_replic) <- c("does not contain 'replic'" = 0, "contains 'replic'" = 1)
val_labels(codebook_data$hyp_from_fulltext) <- c("hypothesis from abstract alone" = 0, "hypothesis from full text" = 1)
val_labels(codebook_data$result_from_fulltext) <- c("result from abstract alone" = 0, "result from full text" = 1)
val_labels(codebook_data$coding_round) <- c("RR pilot" = 0,
"main coding round" = 1,
"SR replacements and late RR additions" = 2,
"second SR replacement" = 3,
"RR protocol replacement" = 4)
val_labels(codebook_data$uses_AS_coding) <- c("uses MS coding" = 0, "uses AS coding" = 1)
val_labels(codebook_data$coded_by_MS) <- c("not coded by MS" = 0, "coded by MS" = 1)
val_labels(codebook_data$evaluation_certainty_MS) <- c("not certain" = 1,
2,
3,
4,
"very certain" = 5)
val_labels(codebook_data$hypothesis_from_fulltext_MS) <- c("hypothesis from abstract alone" = 0, "hypothesis from full text" = 1)
val_labels(codebook_data$result_from_fulltext_MS) <- c("result from abstract alone" = 0, "result from full text" = 1)
val_labels(codebook_data$fulltext_available_MS) <- c("full text not available" = 0, "full text available" = 1)
val_labels(codebook_data$is_replication_old_MS) <- c("does not contain a replication" = 0, "contains a replication" = 1)
val_labels(codebook_data$is_original_old_MS) <- c("does not contain original work" = 0, "contains original work" = 1)
val_labels(codebook_data$coded_by_AS) <- c("not coded by AS" = 0, "coded by AS" = 1)
val_labels(codebook_data$evaluation_certainty_AS) <- c("not certain" = 1,
2,
3,
4,
"very certain" = 5)
val_labels(codebook_data$hypothesis_from_fulltext_AS) <- c("hypothesis from abstract alone" = 0, "hypothesis from full text" = 1)
val_labels(codebook_data$result_from_fulltext_AS) <- c("result from abstract alone" = 0, "result from full text" = 1)
val_labels(codebook_data$fulltext_available_AS) <- c("full text not available" = 0, "full text available" = 1)
val_labels(codebook_data$is_replication_old_AS) <- c("does not contain a replication" = 0, "contains a replication" = 1)
val_labels(codebook_data$is_original_old_AS) <- c("does not contain original work" = 0, "contains original work" = 1)
val_labels(codebook_data$is_replication_new_coded_by_AS) <- c("replication status not coded by AS" = 0, "replication status coded by AS" = 1)
val_labels(codebook_data$is_replication_new_AS) <- c("is not a replication" = 0, "is a replication" = 1)
val_labels(codebook_data$is_replication_new_coded_by_DL) <- c("replication status not coded by DL" = 0, "replication status coded by DL" = 1)
val_labels(codebook_data$is_replication_new_DL) <- c("is not a replication" = 0, "is a replication" = 1)
val_labels(codebook_data$is_replication_special_issue) <- c("not part of replication special issue" = 0, "part of replication special issue" = 1)
val_labels(codebook_data$hypothesis_intro_contains_replic) <- c("hypothesis intro does not contain 'replic'" = 0, "hypothesis intro contains 'replic'" = 1)
# Add meta data
metadata(codebook_data)$name <- "Positive Results in Standard vs Registered Reports"
metadata(codebook_data)$description <- "Coded variables to compare the proportion of papers that find support for their first tested hypothesis between Registered Reports and standard reports in Psychology"
metadata(codebook_data)$creator <- list(
"@type" = "Person",
givenName = "Anne", familyName = "Scheel",
affiliation = list("@type" = "Organization",
name = "Eindhoven University of Technology"),
"@type" = "Person",
givenName = " Mitchell", familiyName = "Schijen",
"@type" = "Person",
givenName = "Daniël", familiyName = "Lakens")
metadata(codebook_data)$temporalCoverage <- "Winter 2018"
#Export codebook
rio::export(codebook_data, "positive_results_in_registered_reports_data.rds") # to R data structure file
codebook(codebook_data)
knitr::asis_output(data_info)
if (exists("name", meta)) {
glue::glue(
"__Dataset name__: {name}",
.envir = meta)
}
Dataset name: Positive Results in Standard vs Registered Reports
cat(description)
Coded variables to compare the proportion of papers that find support for their first tested hypothesis between Registered Reports and standard reports in Psychology
Metadata for search engines
Temporal Coverage: Winter 2018
Date published: 2020-01-13
Creator:
affiliation:
familiyName: Lakens
meta <- meta[setdiff(names(meta),
c("creator", "datePublished", "identifier",
"url", "citation", "spatialCoverage",
"temporalCoverage", "description", "name"))]
pander::pander(meta)
knitr::asis_output(survey_overview)
if (detailed_variables || detailed_scales) {
knitr::asis_output(paste0(scales_items, sep = "\n\n\n", collapse = "\n\n\n"))
}
ID number
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| id | ID number | numeric | 0 | 1 | 1 | 122 | 243 | 122 | 70.29225 | ▇▇▇▇▇ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether paper is included in final analysis
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| include_in_analysis | whether paper is included in final analysis | haven_labelled | 0. excluded, 1. included |
0 | 1 | 0 | 1 | 1 | 0.9176955 | 0.2753954 | 2 | ▁▁▁▁▁▁▁▇ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
reason for exclusion
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
223 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| exclusion_crit | reason for exclusion | character | 223 | 0.0823045 | 5 | 0 | 3 | 24 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
Registered Report (RR) or standard report (SR)
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| is_RR | Registered Report (RR) or standard report (SR) | haven_labelled | 0. SR, 1. RR |
0 | 1 | 0 | 0 | 1 | 0.345679 | 0.4765708 | 2 | ▇▁▁▁▁▁▁▅ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
if the coded hypothesis received no support, partial support, or full support
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| support | if the coded hypothesis received no support, partial support, or full support | character | 0 | 1 | 4 | 0 | 7 | 15 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether the coded hypothesis was at least partially supported or not
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
20 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| support_binary | whether the coded hypothesis was at least partially supported or not | haven_labelled | 0. no support, 1. partial or full support |
20 | 0.9176955 | 0 | 1 | 1 | 0.793722 | 0.4055427 | 2 | ▂▁▁▁▁▁▁▇ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether the coded hypothesis is a direct replication of previous work
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
2 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| is_replication | whether the coded hypothesis is a direct replication of previous work | haven_labelled | 0. is not a replication, 1. is a replication |
2 | 0.9917695 | 0 | 0 | 1 | 0.2323651 | 0.4232196 | 2 | ▇▁▁▁▁▁▁▂ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether the full text of the paper (excl. references) contains the string ‘replic’
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| contains_replic | whether the full text of the paper (excl. references) contains the string ‘replic’ | haven_labelled | 0. does not contain ‘replic’, 1. contains ‘replic’ |
0 | 1 | 0 | 1 | 1 | 0.6419753 | 0.480409 | 2 | ▅▁▁▁▁▁▁▇ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
phrase used to introduce/mark the coded hypothesis in RRs; from abstract
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
194 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| RR_hyp_intro_abstract | phrase used to introduce/mark the coded hypothesis in RRs; from abstract | character | 194 | 0.2016461 | 38 | 0 | 13 | 43 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
phrase used to introduce/mark the coded hypothesis in RRs; from full text
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
218 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| RR_hyp_intro_fulltext | phrase used to introduce/mark the coded hypothesis in RRs; from full text | character | 218 | 0.1028807 | 23 | 0 | 2 | 54 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
quote of the coded hypothesis
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
20 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| hypothesis_quote | quote of the coded hypothesis | character | 20 | 0.9176955 | 223 | 0 | 83 | 1464 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
quote of the coded finding or conclusion
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
20 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| result_quote | quote of the coded finding or conclusion | character | 20 | 0.9176955 | 223 | 0 | 27 | 1872 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether hypothesis was coded from abstract or full text
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
18 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| hyp_from_fulltext | whether hypothesis was coded from abstract or full text | haven_labelled | 0. hypothesis from abstract alone, 1. hypothesis from full text |
18 | 0.9259259 | 0 | 0 | 1 | 0.2844444 | 0.4521553 | 2 | ▇▁▁▁▁▁▁▃ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether finding/conclusion was coded from abstract or full text
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
19 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| result_from_fulltext | whether finding/conclusion was coded from abstract or full text | haven_labelled | 0. result from abstract alone, 1. result from full text |
19 | 0.9218107 | 0 | 0 | 1 | 0.34375 | 0.4760226 | 2 | ▇▁▁▁▁▁▁▅ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
digital object identifier (DOI)
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
1 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| doi | digital object identifier (DOI) | character | 1 | 0.9958848 | 242 | 0 | 14 | 38 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
title
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| title | title | character | 0 | 1 | 243 | 0 | 34 | 230 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
publication year
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| year | publication year | numeric | 0 | 1 | 2013 | 2016 | 2018 | 2015.844 | 1.63896 | ▇▃▅▆▆ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
journal the paper is published in
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
1 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| journal | journal the paper is published in | character | 1 | 0.9958848 | 117 | 0 | 6 | 66 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
abstract
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
20 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| abstract | abstract | character | 20 | 0.9176955 | 223 | 0 | 604 | 3107 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
author keywords from meta-data
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
43 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| keywords | author keywords from meta-data | character | 43 | 0.8230453 | 200 | 0 | 26 | 190 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
when the paper was coded (during piloting, in the main round, or as a replacement/late addition)
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| coding_round | when the paper was coded (during piloting, in the main round, or as a replacement/late addition) |
haven_labelled | 0. RR pilot, 1. main coding round, 2. SR replacements and late RR additions, 3. second SR replacement, 4. RR protocol replacement |
0 | 1 | 0 | 1 | 4 | 1.024691 | 0.3740103 | 5 | ▁▇▁▁▁▁▁▁ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
Comments on how MS’ and AS’ codings were combined if there was disagreement
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
170 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| combining_coding_notes | Comments on how MS’ and AS’ codings were combined if there was disagreement | character | 170 | 0.3004115 | 40 | 0 | 47 | 498 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether AS’ or MS’ coding was used for final analysis
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
3 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uses_AS_coding | whether AS’ or MS’ coding was used for final analysis | haven_labelled | 0. uses MS coding, 1. uses AS coding |
3 | 0.9876543 | 0 | 0 | 1 | 0.1833333 | 0.3877482 | 2 | ▇▁▁▁▁▁▁▂ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether MS coded the paper
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| coded_by_MS | whether MS coded the paper | haven_labelled | 0. not coded by MS, 1. coded by MS |
0 | 1 | 0 | 1 | 1 | 0.9876543 | 0.110651 | 2 | ▁▁▁▁▁▁▁▇ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: whether hypothesis was supported (original verdict)
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| support_orig_MS | MS: whether hypothesis was supported (original verdict) | character | 0 | 1 | 4 | 0 | 7 | 15 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: whether hypothesis was supported (revised verdict after discussion with MS)
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
21 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| support_revised_MS | MS: whether hypothesis was supported (revised verdict after discussion with MS) | character | 21 | 0.9135802 | 4 | 0 | 7 | 15 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS’ coding certainty
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
13 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| evaluation_certainty_MS | MS’ coding certainty | haven_labelled | 1. not certain, 2. , 3. , 4. , 5. very certain |
13 | 0.9465021 | 1 | 4 | 5 | 3.582609 | 1.344454 | 5 | ▃▂▁▃▁▇▁▆ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: hypothesis quote
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
16 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| hypothesis_MS | MS: hypothesis quote | character | 16 | 0.9341564 | 227 | 0 | 83 | 1464 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: hypothesis introduction phrase
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
32 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| hypothesis_introduction_MS | MS: hypothesis introduction phrase | character | 32 | 0.8683128 | 94 | 0 | 7 | 126 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: finding quote
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
87 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| finding_MS | MS: finding quote | character | 87 | 0.6419753 | 156 | 0 | 27 | 1402 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: conclusion quote
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
164 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| conclusion_MS | MS: conclusion quote | character | 164 | 0.3251029 | 79 | 0 | 27 | 1729 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: whether hypothesis was coded from abstract or full text
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
18 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| hypothesis_from_fulltext_MS | MS: whether hypothesis was coded from abstract or full text | haven_labelled | 0. hypothesis from abstract alone, 1. hypothesis from full text |
18 | 0.9259259 | 0 | 0 | 1 | 0.3333333 | 0.4724556 | 2 | ▇▁▁▁▁▁▁▃ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: whether finding/conclusion was coded from abstract or full text
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
19 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| result_from_fulltext_MS | MS: whether finding/conclusion was coded from abstract or full text | haven_labelled | 0. result from abstract alone, 1. result from full text |
19 | 0.9218107 | 0 | 0 | 1 | 0.3794643 | 0.4863405 | 2 | ▇▁▁▁▁▁▁▅ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: whether full text was available during coding
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
2 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| fulltext_available_MS | MS: whether full text was available during coding | haven_labelled | 0. full text not available, 1. full text available |
2 | 0.9917695 | 0 | 1 | 1 | 0.8755187 | 0.3308169 | 2 | ▁▁▁▁▁▁▁▇ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: whether paper contains a replication (old variable, not used!)
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
6 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| is_replication_old_MS | MS: whether paper contains a replication (old variable, not used!) | haven_labelled | 0. does not contain a replication, 1. contains a replication |
6 | 0.9753086 | 0 | 0 | 1 | 0.3417722 | 0.4753075 | 2 | ▇▁▁▁▁▁▁▅ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: whether paper contains original research (old variable, not used!)
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
6 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| is_original_old_MS | MS: whether paper contains original research (old variable, not used!) | haven_labelled | 0. does not contain original work, 1. contains original work |
6 | 0.9753086 | 0 | 1 | 1 | 0.8396624 | 0.3676954 | 2 | ▂▁▁▁▁▁▁▇ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: time spent on coding the paper
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
## 27 unique, categorical values, so not shown.
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | min | median | max |
|---|---|---|---|---|---|---|---|---|
| time_spent_MS | MS: time spent on coding the paper | POSIXct | 0 | 1 | 27 | 1899-12-31 00:02:00 | 1899-12-31 00:05:00 | 1899-12-31 00:30:00 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
MS: coding notes/comments
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
88 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| individual_coding_notes_MS | MS: coding notes/comments | character | 88 | 0.6378601 | 153 | 0 | 26 | 842 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether AS coded the paper
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| coded_by_AS | whether AS coded the paper | haven_labelled | 0. not coded by AS, 1. coded by AS |
0 | 1 | 0 | 0 | 1 | 0.3621399 | 0.481611 | 2 | ▇▁▁▁▁▁▁▅ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: whether hypothesis was supported (original verdict)
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
153 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| support_orig_AS | AS: whether hypothesis was supported (original verdict) | character | 153 | 0.3703704 | 8 | 0 | 7 | 28 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: whether hypothesis was supported (revised verdict after discussion with MS)
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
161 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| support_revised_AS | AS: whether hypothesis was supported (revised verdict after discussion with MS) | character | 161 | 0.3374486 | 5 | 0 | 7 | 15 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS’ coding certainty
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
232 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| evaluation_certainty_AS | AS’ coding certainty | haven_labelled | 1. not certain, 2. , 3. , 4. , 5. very certain |
232 | 0.0452675 | 2 | 4 | 5 | 4 | 0.8944272 | 5 | ▁▁▁▁▁▇▁▃ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: hypothesis quote
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
164 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| hypothesis_AS | AS: hypothesis quote | character | 164 | 0.3251029 | 79 | 0 | 26 | 593 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: hypothesis introduction phrase
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
169 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| hypothesis_introduction_AS | AS: hypothesis introduction phrase | character | 169 | 0.3045267 | 40 | 0 | 3 | 54 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: finding quote
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
199 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| finding_AS | AS: finding quote | character | 199 | 0.18107 | 44 | 0 | 98 | 677 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: conclusion quote
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
201 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| conclusion_AS | AS: conclusion quote | character | 201 | 0.1728395 | 42 | 0 | 51 | 542 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: whether hypothesis was coded from abstract or full text
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
168 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| hypothesis_from_fulltext_AS | AS: whether hypothesis was coded from abstract or full text | haven_labelled | 0. hypothesis from abstract alone, 1. hypothesis from full text |
168 | 0.308642 | 0 | 0 | 1 | 0.1466667 | 0.3561556 | 2 | ▇▁▁▁▁▁▁▂ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: whether finding/conclusion was coded from abstract or full text
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
171 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| result_from_fulltext_AS | AS: whether finding/conclusion was coded from abstract or full text | haven_labelled | 0. result from abstract alone, 1. result from full text |
171 | 0.2962963 | 0 | 0 | 1 | 0.25 | 0.4360514 | 2 | ▇▁▁▁▁▁▁▂ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: whether full text was available during coding
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
164 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| fulltext_available_AS | AS: whether full text was available during coding | haven_labelled | 0. full text not available, 1. full text available |
164 | 0.3251029 | 0 | 1 | 1 | 0.9367089 | 0.2450417 | 2 | ▁▁▁▁▁▁▁▇ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: whether paper contains a replication (old variable, not used!)
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
146 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| is_replication_old_AS | AS: whether paper contains a replication (old variable, not used!) | haven_labelled | 0. does not contain a replication, 1. contains a replication |
146 | 0.399177 | 0 | 0 | 1 | 0.2680412 | 0.4452402 | 2 | ▇▁▁▁▁▁▁▃ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: whether paper contains original research (old variable, not used!)
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
146 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| is_original_old_AS | AS: whether paper contains original research (old variable, not used!) | haven_labelled | 0. does not contain original work, 1. contains original work |
146 | 0.399177 | 0 | 1 | 1 | 0.8659794 | 0.3424442 | 2 | ▁▁▁▁▁▁▁▇ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: time spent on coding the paper
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
## 29 unique, categorical values, so not shown.
knitr::opts_chunk$set(fig.height = old_height)
161 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | min | median | max |
|---|---|---|---|---|---|---|---|---|
| time_spent_AS | AS: time spent on coding the paper | POSIXct | 161 | 0.3374486 | 29 | 1899-12-31 00:01:30 | 1899-12-31 00:04:00 | 1899-12-31 00:15:00 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: coding notes/comments
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
202 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| individual_coding_notes_AS | AS: coding notes/comments | character | 202 | 0.1687243 | 38 | 0 | 17 | 489 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
Comments on how AS’ and DL’s new replication codings were combined if there was disagreement
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
235 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| is_replication_new_combining_notes | Comments on how AS’ and DL’s new replication codings were combined if there was disagreement | character | 235 | 0.0329218 | 6 | 0 | 39 | 119 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether AS coded replication status (new variable) for the paper
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| is_replication_new_coded_by_AS | whether AS coded replication status (new variable) for the paper | haven_labelled | 0. replication status not coded by AS, 1. replication status coded by AS |
0 | 1 | 1 | 1 | 1 | 1 | 0 | 2 | ▁▁▁▇▁▁▁▁ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: whether coded hypothesis is a direct replication of previous work
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
1 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| is_replication_new_AS | AS: whether coded hypothesis is a direct replication of previous work | haven_labelled | 0. is not a replication, 1. is a replication |
1 | 0.9958848 | 0 | 0 | 1 | 0.2272727 | 0.4199387 | 2 | ▇▁▁▁▁▁▁▂ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
AS: coding notes/comments re new replication status variable
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
227 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| replic_notes_AS | AS: coding notes/comments re new replication status variable | character | 227 | 0.0658436 | 16 | 0 | 31 | 575 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether DL coded replication status (new variable) for the paper
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| is_replication_new_coded_by_DL | whether DL coded replication status (new variable) for the paper | haven_labelled | 0. replication status not coded by DL, 1. replication status coded by DL |
0 | 1 | 0 | 1 | 1 | 0.5967078 | 0.491571 | 2 | ▆▁▁▁▁▁▁▇ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
DL: whether coded hypothesis is a direct replication of previous work
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
100 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| is_replication_new_DL | DL: whether coded hypothesis is a direct replication of previous work | haven_labelled | 0. is not a replication, 1. is a replication |
100 | 0.5884774 | 0 | 0 | 1 | 0.2307692 | 0.422806 | 2 | ▇▁▁▁▁▁▁▂ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
DL: coding notes/comments re new replication status variable
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
240 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| replic_notes_DL | DL: coding notes/comments re new replication status variable | character | 240 | 0.0123457 | 3 | 0 | 68 | 115 | 0 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether paper is part of a special issue on replication studies
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
0 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| is_replication_special_issue | whether paper is part of a special issue on replication studies | haven_labelled | 0. not part of replication special issue, 1. part of replication special issue |
0 | 1 | 0 | 0 | 1 | 0.1069959 | 0.309746 | 2 | ▇▁▁▁▁▁▁▁ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
whether hypothesis introduction phrase contains ‘replic’
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10
# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)
19 missing values.
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))
| name | label | data_type | value_labels | n_missing | complete_rate | min | median | max | mean | sd | n_value_labels | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| hypothesis_intro_contains_replic | whether hypothesis introduction phrase contains ‘replic’ | haven_labelled | 0. hypothesis intro does not contain ‘replic’, 1. hypothesis intro contains ‘replic’ |
19 | 0.9218107 | 0 | 0 | 1 | 0.0892857 | 0.2857944 | 2 | ▇▁▁▁▁▁▁▁ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}
if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}
if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}
missingness_report
if (length(md_pattern)) {
if (knitr::is_html_output()) {
rmarkdown::paged_table(md_pattern, options = list(rows.print = 10))
} else {
knitr::kable(md_pattern)
}
}
items
export_table(metadata_table)
jsonld
JSON-LD metadata
The following JSON-LD can be found by search engines, if you share this codebook publicly on the web.
{
"name": "Positive Results in Standard vs Registered Reports",
"description": "Coded variables to compare the proportion of papers that find support for their first tested hypothesis between Registered Reports and standard reports in Psychology\n\n\n## Table of variables\nThis table contains variable names, labels, and number of missing values.\nSee the complete codebook for more.\n\n[truncated]\n\n### Note\nThis dataset was automatically described using the [codebook R package](https://rubenarslan.github.io/codebook/) (version 0.8.2).",
"creator": {
"@type": "Person",
"givenName": "Anne",
"familyName": "Scheel",
"affiliation": {
"@type": "Organization",
"name": "Eindhoven University of Technology"
},
"@type.1": "Person",
"givenName.1": " Mitchell",
"familiyName": "Schijen",
"@type.2": "Person",
"givenName.2": "Daniël",
"familiyName.1": "Lakens"
},
"temporalCoverage": "Winter 2018",
"datePublished": "2020-01-13",
"keywords": ["id", "include_in_analysis", "exclusion_crit", "is_RR", "support", "support_binary", "is_replication", "contains_replic", "RR_hyp_intro_abstract", "RR_hyp_intro_fulltext", "hypothesis_quote", "result_quote", "hyp_from_fulltext", "result_from_fulltext", "doi", "title", "authors", "year", "journal", "abstract", "keywords", "coding_round", "combining_coding_notes", "uses_AS_coding", "coded_by_MS", "support_orig_MS", "support_revised_MS", "evaluation_certainty_MS", "hypothesis_MS", "hypothesis_introduction_MS", "finding_MS", "conclusion_MS", "hypothesis_from_fulltext_MS", "result_from_fulltext_MS", "fulltext_available_MS", "is_replication_old_MS", "is_original_old_MS", "time_spent_MS", "individual_coding_notes_MS", "coded_by_AS", "support_orig_AS", "support_revised_AS", "evaluation_certainty_AS", "hypothesis_AS", "hypothesis_introduction_AS", "finding_AS", "conclusion_AS", "hypothesis_from_fulltext_AS", "result_from_fulltext_AS", "fulltext_available_AS", "is_replication_old_AS", "is_original_old_AS", "time_spent_AS", "individual_coding_notes_AS", "is_replication_new_combining_notes", "is_replication_new_coded_by_AS", "is_replication_new_AS", "replic_notes_AS", "is_replication_new_coded_by_DL", "is_replication_new_DL", "replic_notes_DL", "is_replication_special_issue", "hypothesis_intro_contains_replic"],
"@context": "http://schema.org/",
"@type": "Dataset",
"variableMeasured": [
{
"name": "id",
"description": "ID number",
"@type": "propertyValue"
},
{
"name": "include_in_analysis",
"description": "whether paper is included in final analysis",
"value": "0. excluded,\n1. included",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "exclusion_crit",
"description": "reason for exclusion",
"@type": "propertyValue"
},
{
"name": "is_RR",
"description": "Registered Report (RR) or standard report (SR)",
"value": "0. SR,\n1. RR",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "support",
"description": "if the coded hypothesis received no support, partial support, or full support",
"@type": "propertyValue"
},
{
"name": "support_binary",
"description": "whether the coded hypothesis was at least partially supported or not",
"value": "0. no support,\n1. partial or full support",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "is_replication",
"description": "whether the coded hypothesis is a direct replication of previous work",
"value": "0. is not a replication,\n1. is a replication",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "contains_replic",
"description": "whether the full text of the paper (excl. references) contains the string 'replic'",
"value": "0. does not contain 'replic',\n1. contains 'replic'",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "RR_hyp_intro_abstract",
"description": "phrase used to introduce/mark the coded hypothesis in RRs; from abstract",
"@type": "propertyValue"
},
{
"name": "RR_hyp_intro_fulltext",
"description": "phrase used to introduce/mark the coded hypothesis in RRs; from full text",
"@type": "propertyValue"
},
{
"name": "hypothesis_quote",
"description": "quote of the coded hypothesis",
"@type": "propertyValue"
},
{
"name": "result_quote",
"description": "quote of the coded finding or conclusion",
"@type": "propertyValue"
},
{
"name": "hyp_from_fulltext",
"description": "whether hypothesis was coded from abstract or full text",
"value": "0. hypothesis from abstract alone,\n1. hypothesis from full text",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "result_from_fulltext",
"description": "whether finding/conclusion was coded from abstract or full text",
"value": "0. result from abstract alone,\n1. result from full text",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "doi",
"description": "digital object identifier (DOI)",
"@type": "propertyValue"
},
{
"name": "title",
"description": "title",
"@type": "propertyValue"
},
{
"name": "authors",
"description": "author(s) of the paper",
"@type": "propertyValue"
},
{
"name": "year",
"description": "publication year",
"@type": "propertyValue"
},
{
"name": "journal",
"description": "journal the paper is published in",
"@type": "propertyValue"
},
{
"name": "abstract",
"description": "abstract",
"@type": "propertyValue"
},
{
"name": "keywords",
"description": "author keywords from meta-data",
"@type": "propertyValue"
},
{
"name": "coding_round",
"description": "when the paper was coded (during piloting, in the main round, or as a replacement/late addition)\n",
"value": "0. RR pilot,\n1. main coding round,\n2. SR replacements and late RR additions,\n3. second SR replacement,\n4. RR protocol replacement",
"maxValue": 4,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "combining_coding_notes",
"description": "Comments on how MS' and AS' codings were combined if there was disagreement",
"@type": "propertyValue"
},
{
"name": "uses_AS_coding",
"description": "whether AS' or MS' coding was used for final analysis",
"value": "0. uses MS coding,\n1. uses AS coding",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "coded_by_MS",
"description": "whether MS coded the paper",
"value": "0. not coded by MS,\n1. coded by MS",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "support_orig_MS",
"description": "MS: whether hypothesis was supported (original verdict)",
"@type": "propertyValue"
},
{
"name": "support_revised_MS",
"description": "MS: whether hypothesis was supported (revised verdict after discussion with MS)",
"@type": "propertyValue"
},
{
"name": "evaluation_certainty_MS",
"description": "MS' coding certainty",
"value": "1. not certain,\n2. ,\n3. ,\n4. ,\n5. very certain",
"maxValue": 5,
"minValue": 1,
"@type": "propertyValue"
},
{
"name": "hypothesis_MS",
"description": "MS: hypothesis quote",
"@type": "propertyValue"
},
{
"name": "hypothesis_introduction_MS",
"description": "MS: hypothesis introduction phrase",
"@type": "propertyValue"
},
{
"name": "finding_MS",
"description": "MS: finding quote",
"@type": "propertyValue"
},
{
"name": "conclusion_MS",
"description": "MS: conclusion quote",
"@type": "propertyValue"
},
{
"name": "hypothesis_from_fulltext_MS",
"description": "MS: whether hypothesis was coded from abstract or full text",
"value": "0. hypothesis from abstract alone,\n1. hypothesis from full text",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "result_from_fulltext_MS",
"description": "MS: whether finding/conclusion was coded from abstract or full text",
"value": "0. result from abstract alone,\n1. result from full text",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "fulltext_available_MS",
"description": "MS: whether full text was available during coding",
"value": "0. full text not available,\n1. full text available",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "is_replication_old_MS",
"description": "MS: whether paper contains a replication (old variable, not used!)",
"value": "0. does not contain a replication,\n1. contains a replication",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "is_original_old_MS",
"description": "MS: whether paper contains original research (old variable, not used!)",
"value": "0. does not contain original work,\n1. contains original work",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "time_spent_MS",
"description": "MS: time spent on coding the paper",
"@type": "propertyValue"
},
{
"name": "individual_coding_notes_MS",
"description": "MS: coding notes/comments",
"@type": "propertyValue"
},
{
"name": "coded_by_AS",
"description": "whether AS coded the paper",
"value": "0. not coded by AS,\n1. coded by AS",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "support_orig_AS",
"description": "AS: whether hypothesis was supported (original verdict)",
"@type": "propertyValue"
},
{
"name": "support_revised_AS",
"description": "AS: whether hypothesis was supported (revised verdict after discussion with MS)",
"@type": "propertyValue"
},
{
"name": "evaluation_certainty_AS",
"description": "AS' coding certainty",
"value": "1. not certain,\n2. ,\n3. ,\n4. ,\n5. very certain",
"maxValue": 5,
"minValue": 1,
"@type": "propertyValue"
},
{
"name": "hypothesis_AS",
"description": "AS: hypothesis quote",
"@type": "propertyValue"
},
{
"name": "hypothesis_introduction_AS",
"description": "AS: hypothesis introduction phrase",
"@type": "propertyValue"
},
{
"name": "finding_AS",
"description": "AS: finding quote",
"@type": "propertyValue"
},
{
"name": "conclusion_AS",
"description": "AS: conclusion quote",
"@type": "propertyValue"
},
{
"name": "hypothesis_from_fulltext_AS",
"description": "AS: whether hypothesis was coded from abstract or full text",
"value": "0. hypothesis from abstract alone,\n1. hypothesis from full text",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "result_from_fulltext_AS",
"description": "AS: whether finding/conclusion was coded from abstract or full text",
"value": "0. result from abstract alone,\n1. result from full text",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "fulltext_available_AS",
"description": "AS: whether full text was available during coding",
"value": "0. full text not available,\n1. full text available",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "is_replication_old_AS",
"description": "AS: whether paper contains a replication (old variable, not used!)",
"value": "0. does not contain a replication,\n1. contains a replication",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "is_original_old_AS",
"description": "AS: whether paper contains original research (old variable, not used!)",
"value": "0. does not contain original work,\n1. contains original work",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "time_spent_AS",
"description": "AS: time spent on coding the paper",
"@type": "propertyValue"
},
{
"name": "individual_coding_notes_AS",
"description": "AS: coding notes/comments",
"@type": "propertyValue"
},
{
"name": "is_replication_new_combining_notes",
"description": "Comments on how AS' and DL's new replication codings were combined if there was disagreement",
"@type": "propertyValue"
},
{
"name": "is_replication_new_coded_by_AS",
"description": "whether AS coded replication status (new variable) for the paper",
"value": "0. replication status not coded by AS,\n1. replication status coded by AS",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "is_replication_new_AS",
"description": "AS: whether coded hypothesis is a direct replication of previous work",
"value": "0. is not a replication,\n1. is a replication",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "replic_notes_AS",
"description": "AS: coding notes/comments re new replication status variable",
"@type": "propertyValue"
},
{
"name": "is_replication_new_coded_by_DL",
"description": "whether DL coded replication status (new variable) for the paper",
"value": "0. replication status not coded by DL,\n1. replication status coded by DL",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "is_replication_new_DL",
"description": "DL: whether coded hypothesis is a direct replication of previous work",
"value": "0. is not a replication,\n1. is a replication",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "replic_notes_DL",
"description": "DL: coding notes/comments re new replication status variable",
"@type": "propertyValue"
},
{
"name": "is_replication_special_issue",
"description": "whether paper is part of a special issue on replication studies",
"value": "0. not part of replication special issue,\n1. part of replication special issue",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
},
{
"name": "hypothesis_intro_contains_replic",
"description": "whether hypothesis introduction phrase contains 'replic'",
"value": "0. hypothesis intro does not contain 'replic',\n1. hypothesis intro contains 'replic'",
"maxValue": 1,
"minValue": 0,
"@type": "propertyValue"
}
]
}`